Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    platz
    -0.17
     Lehr
    -0.16
    utsch
    -0.16
     Garrison
    -0.15
     Dress
    -0.14
    licht
    -0.14
    rium
    -0.14
    wig
    -0.14
    bidden
    -0.14
     Grande
    -0.14
    POSITIVE LOGITS
    IDGE
    0.19
    marsh
    0.16
    idge
    0.16
     Initialized
    0.16
    ley
    0.16
    çĪµ
    0.15
    hurst
    0.15
     Snape
    0.15
    èª
    0.15
     Davies
    0.15
    Act Density 0.132%

    No Known Activations